{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EQS2B4XDKQ3X7U4Q5KWZWEGI5Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"37607dc17d94dfa0e69ea1441db8a72d1e3c6e6ddd484f045613a9b515c97014","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-16T06:11:00Z","title_canon_sha256":"a67720820a03539b858310649317539068589d7f68a6a47c41b45ee6f48965e7"},"schema_version":"1.0","source":{"id":"2603.14867","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.14867","created_at":"2026-06-11T01:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2603.14867v4","created_at":"2026-06-11T01:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14867","created_at":"2026-06-11T01:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"EQS2B4XDKQ3X","created_at":"2026-06-11T01:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"EQS2B4XDKQ3X7U4Q","created_at":"2026-06-11T01:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"EQS2B4XD","created_at":"2026-06-11T01:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:d045bffe42bfd211f9f27c9d1113d60275114228e35fcf87341da2ed87509298","target":"graph","created_at":"2026-06-11T01:09:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.14867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's s","authors_text":"Akifumi Wachi, Mikoto Kudo, Takumi Tanabe, Youhei Akimoto","cross_cats":["cs.AI","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-16T06:11:00Z","title":"Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14867","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59d6bccb8469c0fcef6d667340fb0bfd7fe235f3ec043562d53258720e068652","target":"record","created_at":"2026-06-11T01:09:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"37607dc17d94dfa0e69ea1441db8a72d1e3c6e6ddd484f045613a9b515c97014","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-16T06:11:00Z","title_canon_sha256":"a67720820a03539b858310649317539068589d7f68a6a47c41b45ee6f48965e7"},"schema_version":"1.0","source":{"id":"2603.14867","kind":"arxiv","version":4}},"canonical_sha256":"2425a0f2e354377fd390eaad9b10c8ee65f8adf0d69ea31df01ca4a840d995c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2425a0f2e354377fd390eaad9b10c8ee65f8adf0d69ea31df01ca4a840d995c8","first_computed_at":"2026-06-11T01:09:33.255419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:33.255419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"urFIndjhWrSDyuQPAKQLryGiTHwnd7g+X5hmUI4oNlaV8QlBRyeTuOanjAkFDffEMVy4bOjCvXxrmY+rDXSsAQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:33.256462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.14867","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59d6bccb8469c0fcef6d667340fb0bfd7fe235f3ec043562d53258720e068652","sha256:d045bffe42bfd211f9f27c9d1113d60275114228e35fcf87341da2ed87509298"],"state_sha256":"0d8b941fbfe01aaf894a9b23a31c4f25c147882c99b45aff112585baa8e900d4"}